name: Java CI with Maven

on:
  push:
    branches:
    - master
    - "*.x"
  pull_request:
    branches:
    - master
    - "*.x"

jobs:
  build:

    runs-on: ubuntu-latest
    env:
      PARENT_BRANCH: main

    steps:
    - uses: actions/checkout@v4
    - name: Set up JDK 21
      uses: actions/setup-java@v4
      with:
        java-version: '21'

    /**
     * Context object containing crawler state and configuration.
     */
    protected CrawlerContext crawlerContext;

    /**
     * Flag indicating whether the crawler runs in background mode.
     */
    protected boolean background = false;

    /**
     * Flag indicating whether crawler threads run as daemon threads.
     */
    protected boolean daemon = false;

/**
 * PdfExtractor extracts text content from PDF files using Apache PDFBox.
 * It supports password-protected PDFs and can extract embedded documents and annotations.
 *
 * <p>The extractor runs text extraction in a separate thread with a configurable timeout
 * to prevent hanging on problematic PDF files. It also extracts metadata from the PDF
 * document and includes it in the extraction result.
 *
 * <p>Features:

     */
    protected void log(final LogHelper logHelper, final LogType key, final Object... objs) {
        if (logHelper != null) {
            logHelper.log(key, objs);
        }
    }

    /**
     * Runs the crawling process in a separate thread.
     * This method fetches URLs from the queue, accesses content, processes responses,
     * and extracts child URLs until the crawling process is done or no more URLs are available.